© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150446
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItem
    -0.25
    éĻ¢éĻ¢éķ¿
    -0.25
    ìĬ¨
    -0.24
    æĬĬè¿ĻäºĽ
    -0.24
    FromString
    -0.24
    áĥ¦
    -0.24
    ahi
    -0.24
     foll
    -0.24
    æĬĬè¿Ļ个
    -0.24
    娱
    -0.23
    POSITIVE LOGITS
    ä¸ŃåįĪ
    0.28
     اÙĦÙħÙĪ
    0.28
     âĶĤ
    0.27
    ropp
    0.27
    é¹Ĭ
    0.27
    ány
    0.26
     intervening
    0.26
    ï¸
    0.26
    azines
    0.25
    èķĥ
    0.25
    Activations Density 0.780%

    No Known Activations

    This feature has no known activations.